Time_Series
-
Adaptive Nonlinear Vector Autoregression: Robust Forecasting for Noisy Chaotic Time Series
2025-07-11 16:40:10Azimov Sherkhon, Susana Lopez-Moreno, Eric Dolores-Cuenca, Sieun Lee, Sangil KimAbstract
Nonlinear vector autoregression (NVAR) and reservoir computing (RC) have shown promise in forecasting chaotic dynamical systems, such as the Lorenz-63 model and El Nino-Southern Oscillation. However, their reliance on fixed nonlinearities - polynomial expansions in NVAR or random feature maps in RC - limits their adaptability to high noise or real-world data. These methods also scale poorly in high-dimensional settings due to costly matrix inversion during readout computation. We propose an adaptive NVAR model that combines delay-embedded linear inputs with features generated by a shallow, learnable multi-layer perceptron (MLP). The MLP and linear readout are jointly trained using gradient-based optimization, enabling the model to learn data-driven nonlinearities while preserving a simple readout structure. Unlike standard NVAR, our approach avoids the need for an exhaustive and sensitive grid search over ridge and delay parameters. Instead, tuning is restricted to neural network hyperparameters, improving scalability. Initial experiments on chaotic systems tested under noise-free and synthetically noisy conditions showed that the adaptive model outperformed the standard NVAR in predictive accuracy and showed robust forecasting under noisy conditions with a lower observation frequency.
Abstract (translated)
非线性向量自回归（NVAR）和液池计算（RC）在预测洛伦兹-63模型和厄尔尼诺南方涛动等混沌动力系统方面显示出潜力。然而，它们依赖于固定的非线性机制——NVAR中的多项式展开或RC中的随机特征映射——限制了这些方法对高噪声或真实世界数据的适应能力。在高维设置中，由于读取计算期间需要进行昂贵的矩阵求逆操作，这类方法的表现也较差。 我们提出了一种自适应的NVAR模型，该模型结合了延迟嵌入线性输入和浅层、可学习的多层感知机（MLP）生成的特征。通过基于梯度的优化技术联合训练MLP和线性读取部分，使模型能够从数据中学习非线性特性的同时保持简单的读取结构。与标准NVAR不同，我们的方法避免了对岭参数和延迟参数进行繁琐且敏感的网格搜索调整。相反，调整仅限于神经网络超参数，从而提高了可扩展性。 在无噪声和人工添加噪音的情况下，混沌系统的初步实验表明，自适应模型在预测准确性方面优于标准NVAR，并能在噪声条件下以较低的观测频率实现稳健的预测。
URL
https://arxiv.org/abs/2507.08738
PDF
-
To Trade or Not to Trade: An Agentic Approach to Estimating Market Risk Improves Trading Decisions
2025-07-11 13:29:32Dimitrios Emmanoulopoulos, Ollie Olby, Justin Lyon, Namid R. StillmanAbstract
Large language models (LLMs) are increasingly deployed in agentic frameworks, in which prompts trigger complex tool-based analysis in pursuit of a goal. While these frameworks have shown promise across multiple domains including in finance, they typically lack a principled model-building step, relying instead on sentiment- or trend-based analysis. We address this gap by developing an agentic system that uses LLMs to iteratively discover stochastic differential equations for financial time series. These models generate risk metrics which inform daily trading decisions. We evaluate our system in both traditional backtests and using a market simulator, which introduces synthetic but causally plausible price paths and news events. We find that model-informed trading strategies outperform standard LLM-based agents, improving Sharpe ratios across multiple equities. Our results show that combining LLMs with agentic model discovery enhances market risk estimation and enables more profitable trading decisions.
Abstract (translated)
大型语言模型（LLMs）越来越多地被部署在代理框架中，在这些框架中，提示会触发基于工具的复杂分析以实现目标。尽管这些框架在包括金融在内的多个领域展示了潜力，但它们通常缺乏一个有原则的建模构建步骤，而是依赖于情感或趋势分析。我们通过开发一种使用LLMs迭代发现随机微分方程来填补这一空白，用于金融时间序列。这些模型生成风险指标，为每日交易决策提供信息。我们在传统的回测和市场模拟器中评估了我们的系统，后者引入了合成但因果合理的价格路径和新闻事件。我们发现基于模型的交易策略优于标准的LLM代理，在多个股票上提高了夏普比率（Sharpe ratio）。我们的结果显示，将LLMs与代理模型发现相结合可以增强市场的风险估计，并有助于做出更盈利的交易决策。
URL
https://arxiv.org/abs/2507.08584
PDF
-
On the capabilities of LLMs for classifying and segmenting time series of fruit picking motions into primitive actions
2025-07-10 13:25:18Eleni Konstantinidou, Nikolaos Kounalakis, Nikolaos Efstathopoulos, Dimitrios PapageorgiouAbstract
Despite their recent introduction to human society, Large Language Models (LLMs) have significantly affected the way we tackle mental challenges in our everyday lives. From optimizing our linguistic communication to assisting us in making important decisions, LLMs, such as ChatGPT, are notably reducing our cognitive load by gradually taking on an increasing share of our mental activities. In the context of Learning by Demonstration (LbD), classifying and segmenting complex motions into primitive actions, such as pushing, pulling, twisting etc, is considered to be a key-step towards encoding a task. In this work, we investigate the capabilities of LLMs to undertake this task, considering a finite set of predefined primitive actions found in fruit picking operations. By utilizing LLMs instead of simple supervised learning or analytic methods, we aim at making the method easily applicable and deployable in a real-life scenario. Three different fine-tuning approaches are investigated, compared on datasets captured kinesthetically, using a UR10e robot, during a fruit-picking scenario.
Abstract (translated)
尽管大型语言模型（LLM）最近才被引入人类社会，它们已经在我们日常生活中解决心理挑战的方式上产生了重大影响。从优化我们的语言交流到帮助我们在重要决策中做出选择，像ChatGPT这样的LLM通过逐渐承担越来越多的心理活动，显著减轻了我们的认知负荷。 在基于示范学习（LbD）的背景下，将复杂的动作分类和分割为基本的动作单元，如推动、拉动、扭转等，被视为编码任务的关键步骤。在这项工作中，我们探讨了LLM执行此类任务的能力，并考虑了一个有限的基本动作集，这些动作是在水果采摘操作中发现的。通过使用LLM而不是简单的监督学习或分析方法，我们的目标是使这种方法在现实生活场景中易于应用和部署。 本文研究了三种不同的微调方法，在由UR10e机器人在水果采摘场景中捕捉到的数据集中进行比较和评估。
URL
https://arxiv.org/abs/2507.07745
PDF
-
Action Unit Enhance Dynamic Facial Expression Recognition
2025-07-10 11:59:43Feng Liu, Lingna Gu, Chen Shi, Xiaolan FuAbstract
Dynamic Facial Expression Recognition(DFER) is a rapidly evolving field of research that focuses on the recognition of time-series facial expressions. While previous research on DFER has concentrated on feature learning from a deep learning perspective, we put forward an AU-enhanced Dynamic Facial Expression Recognition architecture, namely AU-DFER, that incorporates AU-expression knowledge to enhance the effectiveness of deep learning modeling. In particular, the contribution of the Action Units(AUs) to different expressions is quantified, and a weight matrix is designed to incorporate a priori knowledge. Subsequently, the knowledge is integrated with the learning outcomes of a conventional deep learning network through the introduction of AU loss. The design is incorporated into the existing optimal model for dynamic expression recognition for the purpose of validation. Experiments are conducted on three recent mainstream open-source approaches to DFER on the principal datasets in this field. The results demonstrate that the proposed architecture outperforms the state-of-the-art(SOTA) methods without the need for additional arithmetic and generally produces improved results. Furthermore, we investigate the potential of AU loss function redesign to address data label imbalance issues in established dynamic expression datasets. To the best of our knowledge, this is the first attempt to integrate quantified AU-expression knowledge into various DFER models. We also devise strategies to tackle label imbalance, or minor class problems. Our findings suggest that employing a diverse strategy of loss function design can enhance the effectiveness of DFER. This underscores the criticality of addressing data imbalance challenges in mainstream datasets within this domain. The source code is available at this https URL.
Abstract (translated)
动态面部表情识别（DFER）是一个迅速发展的研究领域，专注于时间序列的面部表情识别。尽管之前关于DFER的研究主要集中在从深度学习角度进行特征学习上，我们提出了一种增强型动作单元（AU）的动态面部表情识别架构，即AU-DFER，该架构通过整合动作单元表达知识来提升深度学习模型的有效性。具体而言，量化了动作单元对不同表情贡献的程度，并设计了一个权重矩阵以纳入先验知识。随后，通过引入AU损失函数将这些知识与传统深度学习网络的学习结果相结合。此设计被融入现有的动态表情识别最优模型中进行验证。 我们在该领域的三个主要公开数据集上针对三种主流的DFER方法进行了实验。结果显示，所提出的架构优于最新的研究成果（SOTA）方法，并且在不增加额外计算的前提下通常能产生更好的效果。此外，我们还探索了重新设计AU损失函数以解决现有动态表情数据集中标签不平衡问题的潜力。 据我们所知，这是首次尝试将量化后的动作单元表达知识整合到各种DFER模型中的努力。我们也制定了策略来应对标签不平衡或少数类别的问题。我们的研究结果表明，采用多样化的损失函数设计方案可以提升DFER的有效性，并强调了在主流数据集中解决数据不平衡挑战的重要性。 源代码可在[此处](https://URL)获取。（请将URL替换为实际链接地址）
URL
https://arxiv.org/abs/2507.07678
PDF
-
Towards Interpretable Time Series Foundation Models
2025-07-10 05:29:34Matthieu Boileau, Philippe Helluy, Jeremy Pawlus, Svitlana VyetrenkoAbstract
In this paper, we investigate the distillation of time series reasoning capabilities into small, instruction-tuned language models as a step toward building interpretable time series foundation models. Leveraging a synthetic dataset of mean-reverting time series with systematically varied trends and noise levels, we generate natural language annotations using a large multimodal model and use these to supervise the fine-tuning of compact Qwen models. We introduce evaluation metrics that assess the quality of the distilled reasoning - focusing on trend direction, noise intensity, and extremum localization - and show that the post-trained models acquire meaningful interpretive capabilities. Our results highlight the feasibility of compressing time series understanding into lightweight, language-capable models suitable for on-device or privacy-sensitive deployment. This work contributes a concrete foundation toward developing small, interpretable models that explain temporal patterns in natural language.
Abstract (translated)
在这篇论文中，我们研究了将时间序列推理能力提炼到小型指令调优语言模型中的方法，以朝着构建可解释的时间序列基础模型迈进。通过使用一个合成的数据集——该数据集中包含一系列具有系统变化的趋势和噪声水平的均值回复型时间序列，我们利用大型多模态模型生成自然语言注释，并用这些注释来监督紧凑型Qwen模型的微调过程。我们引入了评估提炼推理质量的指标，重点关注趋势方向、噪声强度以及极值定位，并展示了经过后期训练的模型获得了有意义的解释能力。我们的研究结果强调了将时间序列理解压缩到轻量级且具备语言能力的模型中的可行性，这些模型适合在设备上或在隐私敏感的应用场景中部署。这项工作为开发小型、可解释的模型奠定了基础，这类模型可以以自然语言的形式解释时间模式。
URL
https://arxiv.org/abs/2507.07439
PDF
-
Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow Matching
2025-07-09 18:03:31Huibo Xu, Runlong Yu, Likang Wu, Xianquan Wang, Qi LiuAbstract
Diffusion models, a type of generative model, have shown promise in time series forecasting. But they face limitations like rigid source distributions and limited sampling paths, which hinder their performance. Flow matching offers faster generation, higher-quality outputs, and greater flexibility, while also possessing the ability to utilize valuable information from the prediction errors of prior models, which were previously inaccessible yet critically important. To address these challenges and fully unlock the untapped potential of flow matching, we propose Conditional Guided Flow Matching (CGFM). CGFM extends flow matching by incorporating the outputs of an auxiliary model, enabling a previously unattainable capability in the field: learning from the errors of the auxiliary model. For time series forecasting tasks, it integrates historical data as conditions and guidance, constructs two-sided conditional probability paths, and uses a general affine path to expand the space of probability paths, ultimately leading to improved predictions. Extensive experiments show that CGFM consistently enhances and outperforms state-of-the-art models, highlighting its effectiveness in advancing forecasting methods.
Abstract (translated)
扩散模型作为一种生成模型，在时间序列预测方面展现出了潜力，但它们面临着诸如源分布僵化和采样路径有限等问题，这些问题限制了其性能的提升。流匹配（Flow Matching）方法则提供了一种更快的生成方式、更高的输出质量和更大的灵活性，并且能够利用之前难以获取却至关重要的先前模型预测误差中的有价值信息。为了应对这些挑战并充分释放流匹配的未开发潜力，我们提出了条件引导流匹配（Conditional Guided Flow Matching, CGFM）。CGFM通过引入辅助模型的输出来扩展流匹配方法，从而实现了一种此前无法达到的能力：从辅助模型的错误中学习。 对于时间序列预测任务，CGFM将历史数据作为条件和指导，构建双向条件概率路径，并采用通用仿射路径扩展了概率路径的空间。最终，这种方法带来了改进后的预测效果。广泛的实验表明，与现有最先进的模型相比，CGFM在各种情况下都能持续增强并超越它们，突显出其在推进预测方法方面的有效性。
URL
https://arxiv.org/abs/2507.07192
PDF
-
Generating Multi-Table Time Series EHR from Latent Space with Minimal Preprocessing
2025-07-09 16:22:22Eunbyeol Cho, Jiyoun Kim, Minjae Lee, Sungjin Park, Edward ChoiAbstract
Electronic Health Records (EHR) are time-series relational databases that record patient interactions and medical events over time, serving as a critical resource for healthcare research and applications. However, privacy concerns and regulatory restrictions limit the sharing and utilization of such sensitive data, necessitating the generation of synthetic EHR datasets. Unlike previous EHR synthesis methods, which typically generate medical records consisting of expert-chosen features (e.g. a few vital signs or structured codes only), we introduce RawMed, the first framework to synthesize multi-table, time-series EHR data that closely resembles raw EHRs. Using text-based representation and compression techniques, RawMed captures complex structures and temporal dynamics with minimal preprocessing. We also propose a new evaluation framework for multi-table time-series synthetic EHRs, assessing distributional similarity, inter-table relationships, temporal dynamics, and privacy. Validated on two open-source EHR datasets, RawMed outperforms baseline models in fidelity and utility. The code is available at this https URL.
Abstract (translated)
电子健康记录（EHR）是时间序列关系数据库，用于记录患者互动和医疗事件随时间的变化情况，是医疗研究与应用的重要资源。然而，隐私问题和监管限制阻碍了此类敏感数据的共享和利用，因此产生了生成合成EHR数据集的需求。不同于以往的EHR生成方法通常只生成由专家选定特征构成的病历记录（例如一些重要的生命体征或结构化代码），我们引入了RawMed这一框架，这是首个能够合成类似原始EHR的多表时间序列EHR数据的框架。通过采用基于文本的表示和压缩技术，RawMed在极少预处理的情况下捕捉到了复杂的结构和时间动态变化特征。此外，我们也提出了评估多表时间序列合成EHR的新评价体系，从分布相似性、跨表关系、时间动态以及隐私保护等角度进行综合考量。在两个开源EHR数据集上验证后，RawMed在准确性与实用性方面均超越了基线模型的性能表现。该代码可在[提供的链接]获取。
URL
https://arxiv.org/abs/2507.06996
PDF
-
Elite Polarization in European Parliamentary Speeches: a Novel Measurement Approach Using Large Language Models
2025-07-09 08:44:29Gennadii IakovlevAbstract
This project introduces a new measure of elite polarization via actor and subject detection using artificial intelligence. I identify when politicians mention one another in parliamentary speeches, note who is speaking and who is being addressed, and assess the emotional temperature behind these evaluations. This maps how elites evaluate their various out-parties, allowing us to create an index of mutual out-party hostility, that is, elite polarization. While I analyzed polarization data over the past four decades for the UK, and two decades for Hungary and Italy, my approach lays the groundwork for a twenty-year, EU-wide time-series dataset on elite polarization. I obtain the results that can be aggregated by party and quarter. The resulting index demonstrates a good face validity: it reacts to events such as electoral campaigns, country- and party-level crises, and to parties losing and assuming power.
Abstract (translated)
该项目通过使用人工智能进行角色和主题检测，引入了一种新的精英分化衡量标准。我识别出政客在议会演讲中提及彼此的情况，并记录发言者及被提及的人的身份，同时评估这些言论背后的情感温度。这描绘了精英阶层如何评价不同的反对派，从而让我们能够创建一个相互反对派敌意指数，即精英分化的指标。虽然我已经分析了过去四十年英国的分化数据、二十年匈牙利和意大利的数据，但我的方法为构建一个涵盖整个欧盟范围内长达二十年的精英分化时间序列数据库奠定了基础。我获取的结果可以按政党及季度进行汇总。由此产生的指数具有良好的表面效度：它对选举活动、国家和政党的危机以及政党失去或获得权力等事件做出了响应。
URL
https://arxiv.org/abs/2507.06658
PDF
-
MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models
2025-07-09 03:00:56Yiwen Liu, Chenyu Zhang, Junjie Song, Siqi Chen, Sun Yin, Zihan Wang, Lingming Zeng, Yuji Cao, Junming JiaoAbstract
As a prominent data modality task, time series forecasting plays a pivotal role in diverse applications. With the remarkable advancements in Large Language Models (LLMs), the adoption of LLMs as the foundational architecture for time series modeling has gained significant attention. Although existing models achieve some success, they rarely both model time and frequency characteristics in a pretraining-finetuning paradigm leading to suboptimal performance in predictions of complex time series, which requires both modeling periodicity and prior pattern knowledge of signals. We propose MoFE-Time, an innovative time series forecasting model that integrates time and frequency domain features within a Mixture of Experts (MoE) network. Moreover, we use the pretraining-finetuning paradigm as our training framework to effectively transfer prior pattern knowledge across pretraining and finetuning datasets with different periodicity distributions. Our method introduces both frequency and time cells as experts after attention modules and leverages the MoE routing mechanism to construct multidimensional sparse representations of input signals. In experiments on six public benchmarks, MoFE-Time has achieved new state-of-the-art performance, reducing MSE and MAE by 6.95% and 6.02% compared to the representative methods Time-MoE. Beyond the existing evaluation benchmarks, we have developed a proprietary dataset, NEV-sales, derived from real-world business scenarios. Our method achieves outstanding results on this dataset, underscoring the effectiveness of the MoFE-Time model in practical commercial applications.
Abstract (translated)
作为重要的数据模态任务，时间序列预测在各种应用中扮演着关键角色。随着大型语言模型（LLMs）的显著进步，将其作为时间序列建模的基础架构已经引起了广泛关注。尽管现有的模型取得了一些成功，但它们很少同时在预训练-微调范式下捕捉时间和频率特性，这导致了对复杂时间序列预测性能不佳的问题，这些复杂的序列需要同时处理周期性和先前信号模式的知识。 为此，我们提出了MoFE-Time，这是一种创新的时间序列预测模型，它将时间与频域特征集成在一个专家混合（MoE）网络中。此外，我们采用预训练-微调范式作为训练框架，以有效跨不同周期分布的预训练和微调数据集转移先前模式知识。我们的方法在注意力模块之后引入了频率和时间单元作为专家，并利用MoE路由机制构建输入信号的多维稀疏表示。 在六个公共基准测试中，MoFE-Time取得了新的最先进的性能，在与代表性的Time-MoE模型相比时，分别将均方误差（MSE）和平均绝对误差（MAE）降低了6.95% 和 6.02%。除了现有的评估基准之外，我们还开发了一个专有数据集NEV-sales，该数据集来源于实际商业场景。在这一数据集中，我们的方法取得了卓越的结果，这进一步证明了MoFE-Time模型在实际商业应用中的有效性。
URL
https://arxiv.org/abs/2507.06502
PDF
-
AI-Based Demand Forecasting and Load Balancing for Optimising Energy use in Healthcare Systems: A real case study
2025-07-08 15:16:50Iman Rahimi, Isha PatelAbstract
This paper tackles the urgent need for efficient energy management in healthcare facilities, where fluctuating demands challenge operational efficiency and sustainability. Traditional methods often prove inadequate, causing inefficiencies and higher costs. To address this, the study presents an AI-based framework combining Long Short-Term Memory (LSTM), genetic algorithm (GA), and SHAP (Shapley Additive Explanations), specifically designed for healthcare energy management. Although LSTM is widely used for time-series forecasting, its application in healthcare energy prediction remains underexplored. The results reveal that LSTM significantly outperforms ARIMA and Prophet models in forecasting complex, non-linear demand patterns. LSTM achieves a Mean Absolute Error (MAE) of 21.69 and Root Mean Square Error (RMSE) of 29.96, far better than Prophet (MAE: 59.78, RMSE: 81.22) and ARIMA (MAE: 87.73, RMSE: 125.22), demonstrating superior performance. The genetic algorithm is applied to optimize model parameters and improve load balancing strategies, enabling adaptive responses to real-time energy fluctuations. SHAP analysis further enhances model transparency by explaining the influence of different features on predictions, fostering trust in decision-making processes. This integrated LSTM-GA-SHAP approach offers a robust solution for improving forecasting accuracy, boosting energy efficiency, and advancing sustainability in healthcare facilities. Future research may explore real-time deployment and hybridization with reinforcement learning for continuous optimization. Overall, the study establishes a solid foundation for using AI in healthcare energy management, highlighting its scalability, efficiency, and resilience potential.
Abstract (translated)
本文针对医疗设施中迫切需要高效的能源管理问题进行了探讨，其中需求波动挑战了运营效率和可持续性。传统方法往往不足以应对这些挑战，导致低效和成本增加。为解决这些问题，本研究提出了一种基于人工智能的框架，结合长短期记忆网络（LSTM）、遗传算法（GA）以及SHAP（Shapley Additive Explanations），专门用于医疗能源管理。尽管LSTM在时间序列预测中得到广泛应用，但其在医疗能耗预测中的应用尚未被充分探索。 研究结果表明，LSTM模型在预测复杂、非线性的需求模式方面显著优于ARIMA和Prophet模型。具体而言，LSTM的平均绝对误差（MAE）为21.69，均方根误差（RMSE）为29.96，远优于Prophet（MAE：59.78，RMSE：81.22）和ARIMA（MAE：87.73，RMSE：125.22），显示出了卓越的性能。遗传算法被用于优化模型参数并改进负载平衡策略，从而使系统能够对实时能源波动做出适应性响应。SHAP分析进一步提升了模型透明度，解释了不同特征对预测结果的影响，增强了决策过程中的信任度。 这种集成LSTM-GA-SHAP的方法为提高预测准确性、增强能源效率和推动医疗设施可持续发展提供了一种稳健的解决方案。未来的研究可能会探索其实时部署以及与强化学习相结合的可能性，以实现持续优化。总的来说，本研究为在医疗能源管理中使用人工智能奠定了坚实的基础，并突显了其可扩展性、高效性和潜在韧性。
URL
https://arxiv.org/abs/2507.06077
PDF
-
Decomposing the Time Series Forecasting Pipeline: A Modular Approach for Time Series Representation, Information Extraction, and Projection
2025-07-08 11:26:42Robert Leppich, Michael Stenger, Andr\'e Bauer, Samuel KounevAbstract
With the advent of Transformers, time series forecasting has seen significant advances, yet it remains challenging due to the need for effective sequence representation, memory construction, and accurate target projection. Time series forecasting remains a challenging task, demanding effective sequence representation, meaningful information extraction, and precise future projection. Each dataset and forecasting configuration constitutes a distinct task, each posing unique challenges the model must overcome to produce accurate predictions. To systematically address these task-specific difficulties, this work decomposes the time series forecasting pipeline into three core stages: input sequence representation, information extraction and memory construction, and final target projection. Within each stage, we investigate a range of architectural configurations to assess the effectiveness of various modules, such as convolutional layers for feature extraction and self-attention mechanisms for information extraction, across diverse forecasting tasks, including evaluations on seven benchmark datasets. Our models achieve state-of-the-art forecasting accuracy while greatly enhancing computational efficiency, with reduced training and inference times and a lower parameter count. The source code is available at this https URL.
Abstract (translated)
随着Transformer模型的出现，时间序列预测取得了显著进步，但由于需要有效的序列表示、内存构建和准确的目标投影，这一任务仍然具有挑战性。时间序列预测仍然是一个艰巨的任务，它要求有效的时间序列表示、有意义的信息提取以及精确的未来预测。每个数据集和预测配置都构成了一项独特的任务，模型必须克服这些特有的挑战以生成准确的预测。 为了系统地解决这些问题，这项工作将时间序列预测流程分解为三个核心阶段：输入序列表示、信息提取及内存构建、最终目标投影。在每个阶段中，我们研究了一系列架构配置，评估诸如卷积层用于特征抽取和自注意力机制用于信息抽取等各种模块的有效性，并涵盖多种预测任务，在七个基准数据集上进行了评估。 我们的模型达到了最先进的预测准确性，同时大大提高了计算效率，通过减少训练和推断时间以及降低参数数量来实现。源代码可在此网址获取：[此处应为实际的URL链接]。
URL
https://arxiv.org/abs/2507.05891
PDF
-
Causal Foundation Models: Disentangling Physics from Instrument Properties
2025-07-07 18:00:00Jeroen Audenaert, Daniel Muthukrishna, Paul F. Gregory, David W. Hogg, V. Ashley VillarAbstract
Foundation models for structured time series data must contend with a fundamental challenge: observations often conflate the true underlying physical phenomena with systematic distortions introduced by measurement instruments. This entanglement limits model generalization, especially in heterogeneous or multi-instrument settings. We present a causally-motivated foundation model that explicitly disentangles physical and instrumental factors using a dual-encoder architecture trained with structured contrastive learning. Leveraging naturally occurring observational triplets (i.e., where the same target is measured under varying conditions, and distinct targets are measured under shared conditions) our model learns separate latent representations for the underlying physical signal and instrument effects. Evaluated on simulated astronomical time series designed to resemble the complexity of variable stars observed by missions like NASA's Transiting Exoplanet Survey Satellite (TESS), our method significantly outperforms traditional single-latent space foundation models on downstream prediction tasks, particularly in low-data regimes. These results demonstrate that our model supports key capabilities of foundation models, including few-shot generalization and efficient adaptation, and highlight the importance of encoding causal structure into representation learning for structured data.
Abstract (translated)
结构化时间序列数据的基础模型必须应对一个根本性的挑战：观测值通常将真实的物理现象与测量仪器引入的系统性偏差混淆在一起。这种纠缠限制了模型的泛化能力，尤其是在异构或多种仪器环境中更为明显。我们提出了一种基于因果动机的基础模型，该模型通过双编码器架构和结构化的对比学习显式地分离了物理因素和仪器效应。利用自然发生的观测三元组（即在不同条件下测量同一目标，在相同条件下测量不同的目标），我们的模型学会了为潜在的物理信号和仪器效果分别建立独立的表示。 我们在模拟天文时间序列数据上进行了评估，这些数据设计成类似于NASA凌日系外行星巡天卫星（TESS）等任务所观测到的变星的复杂性。在低数据量的情况下，我们提出的方法显著优于传统的单潜在空间基础模型，在下游预测任务中表现更佳。 结果表明，我们的模型支持基础模型的关键能力，包括少量样本泛化和高效适应，并强调了在结构化数据表示学习中编码因果结构的重要性。
URL
https://arxiv.org/abs/2507.05333
PDF
-
Solar Flare Prediction Using LSTM and DLSTM with Sliding Window Pattern Recognition
2025-07-07 13:17:38Zeinab Hassani, Davud Mohammadpur, Hossein SafariAbstract
We investigate the use of Long Short-Term Memory (LSTM) and Decomposition-LSTM (DLSTM) networks, combined with an ensemble algorithm, to predict solar flare occurrences using time-series data from the GOES catalog. The dataset spans from 2003 to 2023 and includes 151,071 flare events. Among approximately possible patterns, 7,552 yearly pattern windows are identified, highlighting the challenge of long-term forecasting due to the Sun's complex, self-organized criticality-driven behavior. A sliding window technique is employed to detect temporal quasi-patterns in both irregular and regularized flare time series. Regularization reduces complexity, enhances large flare activity, and captures active days more effectively. To address class imbalance, resampling methods are applied. LSTM and DLSTM models are trained on sequences of peak fluxes and waiting times from irregular time series, while LSTM and DLSTM, integrated with an ensemble approach, are applied to sliding windows of regularized time series with a 3-hour interval. Performance metrics, particularly TSS (0.74), recall (0.95) and the area under the curve (AUC=0.87) in the receiver operating characteristic (ROC), indicate that DLSTM with an ensemble approach on regularized time series outperforms other models, offering more accurate large-flare forecasts with fewer false errors compared to models trained on irregular time series. The superior performance of DLSTM is attributed to its ability to decompose time series into trend and seasonal components, effectively isolating random noise. This study underscores the potential of advanced machine learning techniques for solar flare prediction and highlights the importance of incorporating various solar cycle phases and resampling strategies to enhance forecasting reliability.
Abstract (translated)
我们研究了结合集成算法的长短期记忆网络（LSTM）和分解-LSTM（DLSTM）网络在使用GOES目录的时间序列数据预测太阳耀斑发生情况中的应用。该数据集涵盖了2003年至2023年的时期，包含151,071个耀斑事件。在大约可能的模式中，确定了7,552个年度模式窗口，突显了由于太阳复杂、由自组织临界性驱动的行为导致长期预测面临的挑战。 滑动窗口技术被用于检测不规则和正则化后的耀斑时间序列中的时序准模式。正则化减少了复杂性，并增强了大型耀斑活动的可见度，同时更有效地捕捉活跃日。为解决类别不平衡问题，应用了重采样方法。LSTM 和 DLSTM 模型是在从不规则时间序列中提取的峰值通量和等待时间序列上进行训练的；而与集成方法结合后的 LSTM 和 DLSTM 则被应用于具有3小时间隔窗口的正则化时间序列。 性能指标（特别是TSS（0.74）、召回率（0.95）以及在接收者操作特征（ROC）曲线下的面积(AUC=0.87)）表明，基于正则化时间序列并结合集成方法的DLSTM模型优于其他模型。DLSTM结合集成方法可以提供更准确的大耀斑预测，并且与基于不规则时间序列训练的模型相比，其产生的错误较少。 DLSTM卓越性能的原因在于它能够将时间序列分解为趋势和季节性成分，从而有效隔离随机噪声。这项研究表明了高级机器学习技术在太阳耀斑预测中的潜力，并强调了纳入各种太阳活动周期阶段及重采样策略以增强预测可靠性的必要性。
URL
https://arxiv.org/abs/2507.05313
PDF
-
A Novel Approach for Estimating Positive Lyapunov Exponents in One-Dimensional Chaotic Time Series Using Machine Learning
2025-07-07 10:53:02A. Velichko, M. Belyaev, P. BoriskovAbstract
Understanding and quantifying chaos in nonlinear dynamical systems remains a fundamental challenge in science and engineering. The Lyapunov exponent is a key measure of chaotic behavior, but its accurate estimation from experimental data is often hindered by methodological and computational limitations. In this work, we present a novel machine-learning-based approach for estimating the positive Lyapunov exponent (MLE) from one-dimensional time series, using the growth of out-of-sample prediction errors as a proxy for trajectory divergence. Our method demonstrates high scientific relevance, offering a robust, data-driven alternative to traditional analytic techniques. Through comprehensive testing on several canonical chaotic maps - including the logistic, sine, cubic, and Chebyshev maps - we achieved a coefficient of determination R2pos > 0.9 between predicted and theoretical MLE values for time series as short as M = 200 points. The best accuracy was observed for the Chebyshev map (R2pos = 0.999). Notably, the proposed method maintains high computational efficiency and generalizes well across various machine learning algorithms. These results highlight the significance of our approach for practical chaos analysis in both synthetic and experimental settings, opening new possibilities for robust nonlinear dynamics assessment when only time series data are available.
Abstract (translated)
理解和量化非线性动力系统的混沌行为仍然是科学和工程领域的一个基本挑战。Lyapunov指数是衡量混沌行为的关键指标，但其从实验数据中的准确估计往往受到方法论和计算限制的阻碍。在这项工作中，我们提出了一种基于机器学习的方法，用于从一维时间序列中估算正Lyapunov指数（MLE），通过使用出样本预测误差的增长作为轨迹发散性的替代指标。我们的方法展示了其在科学上的高度相关性，提供了一种比传统分析技术更为稳健和数据驱动的替代方案。通过对几个典型的混沌映射——包括逻辑、正弦、立方和切比雪夫映射——进行详尽测试，我们实现了时间序列长度仅为M=200个点时预测值与理论MLE值之间的决定系数R²_pos > 0.9的良好匹配。在切比雪夫映射中获得了最高的精度（R²_pos = 0.999）。值得注意的是，所提出的方法保持了较高的计算效率，并且能够跨多种机器学习算法很好地泛化。这些结果突显了我们的方法对于人工和实验环境中混沌分析的实际意义，在仅提供时间序列数据的情况下，为非线性动力系统的稳健评估开启了新的可能性。
URL
https://arxiv.org/abs/2507.04868
PDF
-
DisMS-TS: Eliminating Redundant Multi-Scale Features for Time Series Classification
2025-07-07 01:35:55Zhipeng Liu, Peibo Duan, Binwu Wang, Xuan Tang, Qi Chu, Changsheng Zhang, Yongsheng Huang, Bin ZhangAbstract
Real-world time series typically exhibit complex temporal variations, making the time series classification task notably challenging. Recent advancements have demonstrated the potential of multi-scale analysis approaches, which provide an effective solution for capturing these complex temporal patterns. However, existing multi-scale analysis-based time series prediction methods fail to eliminate redundant scale-shared features across multi-scale time series, resulting in the model over- or under-focusing on scale-shared features. To address this issue, we propose a novel end-to-end Disentangled Multi-Scale framework for Time Series classification (DisMS-TS). The core idea of DisMS-TS is to eliminate redundant shared features in multi-scale time series, thereby improving prediction performance. Specifically, we propose a temporal disentanglement module to capture scale-shared and scale-specific temporal representations, respectively. Subsequently, to effectively learn both scale-shared and scale-specific temporal representations, we introduce two regularization terms that ensure the consistency of scale-shared representations and the disparity of scale-specific representations across all temporal scales. Extensive experiments conducted on multiple datasets validate the superiority of DisMS-TS over its competitive baselines, with the accuracy improvement up to 9.71%.
Abstract (translated)
现实世界中的时间序列通常表现出复杂的时序变化，这使得时间序列分类任务具有挑战性。近期的研究进展展示了多尺度分析方法的潜力，这些方法能够有效捕捉这些复杂的时间模式。然而，现有的基于多尺度分析的时间序列预测方法未能消除跨多个时间尺度之间的冗余共享特征，导致模型在处理这些特征时过度或不足关注。为了解决这个问题，我们提出了一种新的端到端分解式多尺度框架（Disentangled Multi-Scale framework for Time Series classification, DisMS-TS）。DisMS-TS的核心思想是消除多尺度时间序列中的冗余共享特征，从而提升预测性能。 具体来说，我们设计了一个时序解耦模块来分别捕捉跨规模的共享时间和特定于每个尺度的时间表示。之后，为了有效地学习这些共享和特有的时间表示，我们引入了两个正则化项：一个确保所有时间尺度上共享表示的一致性；另一个保证各尺度特有表示之间的差异性。 在多个数据集上的广泛实验验证了DisMS-TS相较于竞争基准方法的优越性能，准确率提高了高达9.71%。
URL
https://arxiv.org/abs/2507.04600
PDF
-
DC-Mamber: A Dual Channel Prediction Model based on Mamba and Linear Transformer for Multivariate Time Series Forecasting
2025-07-06 12:58:52Bing Fan, Shusen Ma, Yun-Bo Zhao, Yu KangAbstract
In multivariate time series forecasting (MTSF), existing strategies for processing sequences are typically categorized as channel-independent and channel-mixing. The former treats all temporal information of each variable as a token, focusing on capturing local temporal features of individual variables, while the latter constructs a token from the multivariate information at each time step, emphasizing the modeling of global temporal dependencies. Current mainstream models are mostly based on Transformer and the emerging Mamba. Transformers excel at modeling global dependencies through self-attention mechanisms but exhibit limited sensitivity to local temporal patterns and suffer from quadratic computational complexity, restricting their efficiency in long-sequence processing. In contrast, Mamba, based on state space models (SSMs), achieves linear complexity and efficient long-range modeling but struggles to aggregate global contextual information in parallel. To overcome the limitations of both models, we propose DC-Mamber, a dual-channel forecasting model based on Mamba and linear Transformer for time series forecasting. Specifically, the Mamba-based channel employs a channel-independent strategy to extract intra-variable features, while the Transformer-based channel adopts a channel-mixing strategy to model cross-timestep global dependencies. DC-Mamber first maps the raw input into two distinct feature representations via separate embedding layers. These representations are then processed by a variable encoder (built on Mamba) and a temporal encoder (built on linear Transformer), respectively. Finally, a fusion layer integrates the dual-channel features for prediction. Extensive experiments on eight public datasets confirm DC-Mamber's superior accuracy over existing models.
Abstract (translated)
在多变量时间序列预测（MTSF）中，现有的处理序列策略通常分为通道独立和通道混合两类。前者将每个变量的所有时间信息视为一个标记(token)，侧重于捕捉单个变量的局部时间特征；后者则利用每个时间步长上的多变量信息构造出一个token，强调全局时间依赖性的建模。目前主流模型大多基于Transformer以及新兴的Mamba模型。Transformer通过自注意力机制在建模全局依赖性方面表现出色，但在捕捉局部时间模式方面的敏感度较低，并且面临着二次计算复杂度的问题，这限制了其在长序列处理中的效率。相比之下，基于状态空间模型（SSMs）的Mamba实现了线性复杂度和高效的长程建模，但难以并行地汇总全局上下文信息。 为了克服这两种模型的局限性，我们提出了DC-Mamber，这是一种基于Mamba和线性Transformer的时间序列预测双通道模型。具体来说，基于Mamba的通道采用通道独立策略来提取变量内的特征，而基于Transformer的通道则使用通道混合策略来建模跨时间步长的全局依赖关系。在DC-Mamber中，首先通过单独的嵌入层将原始输入映射为两种不同的特征表示。然后，这些表示分别由一个变量编码器（基于Mamba构建）和一个时间编码器（基于线性Transformer构建）进行处理。最后，融合层整合双通道特征以供预测使用。在八个公开数据集上的广泛实验验证了DC-Mamber相比现有模型具有更高的精度。
URL
https://arxiv.org/abs/2507.04381
PDF
-
Transformer Model for Alzheimer's Disease Progression Prediction Using Longitudinal Visit Sequences
2025-07-05 04:35:04Mahdi Moghaddami, Clayton Schubring, Mohammad-Reza SiadatAbstract
Alzheimer's disease (AD) is a neurodegenerative disorder with no known cure that affects tens of millions of people worldwide. Early detection of AD is critical for timely intervention to halt or slow the progression of the disease. In this study, we propose a Transformer model for predicting the stage of AD progression at a subject's next clinical visit using features from a sequence of visits extracted from the subject's visit history. We also rigorously compare our model to recurrent neural networks (RNNs) such as long short-term memory (LSTM), gated recurrent unit (GRU), and minimalRNN and assess their performances based on factors such as the length of prior visits and data imbalance. We test the importance of different feature categories and visit history, as well as compare the model to a newer Transformer-based model optimized for time series. Our model demonstrates strong predictive performance despite missing visits and missing features in available visits, particularly in identifying converter subjects -- individuals transitioning to more severe disease stages -- an area that has posed significant challenges in longitudinal prediction. The results highlight the model's potential in enhancing early diagnosis and patient outcomes.
Abstract (translated)
阿尔茨海默病（AD）是一种无法治愈的神经退行性疾病，全球有数千万人受其影响。早期检测 AD 对及时干预以阻止或减缓疾病的进展至关重要。在本研究中，我们提出了一种使用来自患者访问历史序列中的特征来预测下一次临床访问时阿尔茨海默病发展阶段的 Transformer 模型。此外，我们严格比较了我们的模型与诸如长短期记忆（LSTM）、门控循环单元（GRU）和 minimalRNN 这样的递归神经网络（RNN），并基于先前访问长度和数据不平衡等因素评估它们的表现。我们测试了不同特征类别和访问历史的重要性，并将模型与其他专为时间序列优化的新型 Transformer 模型进行了比较。尽管存在缺失的访问记录和现有访问中缺失的特征，我们的模型依然表现出强大的预测性能，特别是在识别转换者——即向更严重疾病阶段过渡的个体——这一领域，这对于纵向预测构成了重大挑战。研究结果突显了该模型在改善早期诊断和患者预后方面的潜力。
URL
https://arxiv.org/abs/2507.03899
PDF
-
ReTimeCausal: EM-Augmented Additive Noise Models for Interpretable Causal Discovery in Irregular Time Series
2025-07-04 05:39:50Weihong Li, Anpeng Wu, Kun Kuang, Keting YinAbstract
This paper studies causal discovery in irregularly sampled time series-a pivotal challenge in high-stakes domains like finance, healthcare, and climate science, where missing data and inconsistent sampling frequencies distort causal mechanisms. Traditional methods (e.g., Granger causality, PCMCI) fail to reconcile multi-scale interactions (e.g., hourly storms vs. decadal climate shifts), while neural approaches (e.g., CUTS+) lack interpretability, stemming from a critical gap: existing frameworks either rigidly assume temporal regularity or aggregate dynamics into opaque representations, neglecting real-world granularity and auditable logic. To bridge this gap, we propose ReTimeCausal, a novel integration of Additive Noise Models (ANM) and Expectation-Maximization (EM) that unifies physics-guided data imputation with sparse causal inference. Through kernelized sparse regression and structural constraints, ReTimeCausal iteratively refines missing values (E-step) and causal graphs (M-step), resolving cross-frequency dependencies and missing data issues. Extensive experiments on synthetic and real-world datasets demonstrate that ReTimeCausal outperforms existing state-of-the-art methods under challenging irregular sampling and missing data conditions.
Abstract (translated)
本文研究了在不规则采样时间序列中的因果发现，这是一个在金融、医疗保健和气候科学等高风险领域中至关重要的挑战。在这个领域里，缺失数据和不一致的采样频率扭曲了因果机制。传统的因果发现方法（如格兰杰因果关系法、PCMCI）无法处理跨尺度交互作用（例如，每小时风暴与十年级气候变化之间的相互影响），而神经网络方法（如CUTS+）则缺乏可解释性，原因是现有框架要么刚性地假设时间序列的规律性，要么将动力学聚合为不透明的表示形式，从而忽略了现实世界的细节和可审计逻辑。 为了填补这一空白，我们提出了一种新的方法——ReTimeCausal。该方法结合了加法噪声模型（ANM）与期望最大化算法（EM），整合物理指导的数据插补与稀疏因果推断。通过核化稀疏回归和结构约束，ReTimeCausal能够迭代地完善缺失值（E步）和因果图（M步）。这种方法解决了跨频率依赖性和数据缺失问题。 在合成数据集及真实世界数据集上的广泛实验表明，ReTimeCausal在面对挑战性的不规则采样和缺失数据条件下优于现有的最先进方法。
URL
https://arxiv.org/abs/2507.03310
PDF
-
DeltaSHAP: Explaining Prediction Evolutions in Online Patient Monitoring with Shapley Values
2025-07-03 06:08:07Changhun Kim, Yechan Mun, Sangchul Hahn, Eunho YangAbstract
This study proposes DeltaSHAP, a novel explainable artificial intelligence (XAI) algorithm specifically designed for online patient monitoring systems. In clinical environments, discovering the causes driving patient risk evolution is critical for timely intervention, yet existing XAI methods fail to address the unique requirements of clinical time series explanation tasks. To this end, DeltaSHAP addresses three key clinical needs: explaining the changes in the consecutive predictions rather than isolated prediction scores, providing both magnitude and direction of feature attributions, and delivering these insights in real time. By adapting Shapley values to temporal settings, our approach accurately captures feature coalition effects. It further attributes prediction changes using only the actually observed feature combinations, making it efficient and practical for time-sensitive clinical applications. We also introduce new evaluation metrics to evaluate the faithfulness of the attributions for online time series, and demonstrate through experiments on online patient monitoring tasks that DeltaSHAP outperforms state-of-the-art XAI methods in both explanation quality as 62% and computational efficiency as 33% time reduction on the MIMIC-III decompensation benchmark. We release our code at this https URL.
Abstract (translated)
这项研究提出了一种名为DeltaSHAP的新颖可解释人工智能(XAI)算法，专门针对在线患者监测系统设计。在临床环境中，发现驱动患者风险演变的原因对于及时干预至关重要，然而现有的XAI方法无法满足临床时间序列解释任务的独特需求。为此，DeltaSHAP解决了三个关键的临床需求：解释连续预测的变化而不是孤立的预测分数；提供特征归因的方向和大小；以及实时交付这些见解。 通过将Shapley值适应于时间环境，我们的方法能够准确捕捉到特征联盟效应。此外，该方法仅使用实际观察到的特征组合来分配预测变化，使其对于时间敏感的临床应用既高效又实用。我们还引入了新的评估指标，以评价在线时间序列中归因的真实度，并通过在线患者监测任务上的实验展示了DeltaSHAP在解释质量和计算效率上优于现有的最先进XAI方法：在MIMIC-III脱补偿基准测试中，解释质量提高了62%，计算效率提升了33%的时间减少。我们的代码可在[此处](https://this https URL "请替换URL为实际链接")获得。
URL
https://arxiv.org/abs/2507.02342
PDF
-
CineMyoPS: Segmenting Myocardial Pathologies from Cine Cardiac MR
2025-07-03 03:52:59Wangbin Ding, Lei Li, Junyi Qiu, Bogen Lin, Mingjing Yang, Liqin Huang, Lianming Wu, Sihan Wang, Xiahai ZhuangAbstract
Myocardial infarction (MI) is a leading cause of death worldwide. Late gadolinium enhancement (LGE) and T2-weighted cardiac magnetic resonance (CMR) imaging can respectively identify scarring and edema areas, both of which are essential for MI risk stratification and prognosis assessment. Although combining complementary information from multi-sequence CMR is useful, acquiring these sequences can be time-consuming and prohibitive, e.g., due to the administration of contrast agents. Cine CMR is a rapid and contrast-free imaging technique that can visualize both motion and structural abnormalities of the myocardium induced by acute MI. Therefore, we present a new end-to-end deep neural network, referred to as CineMyoPS, to segment myocardial pathologies, \ie scars and edema, solely from cine CMR images. Specifically, CineMyoPS extracts both motion and anatomy features associated with MI. Given the interdependence between these features, we design a consistency loss (resembling the co-training strategy) to facilitate their joint learning. Furthermore, we propose a time-series aggregation strategy to integrate MI-related features across the cardiac cycle, thereby enhancing segmentation accuracy for myocardial pathologies. Experimental results on a multi-center dataset demonstrate that CineMyoPS achieves promising performance in myocardial pathology segmentation, motion estimation, and anatomy segmentation.
Abstract (translated)
心肌梗死（MI）是全球死亡的主要原因之一。迟发性钆增强（LGE）和T2加权心脏磁共振成像（CMR）可以分别识别瘢痕和水肿区域，这两个因素对于MI的风险分层和预后评估至关重要。虽然结合多序列CMR中的互补信息是有用的，但由于需要使用对比剂等原因，获取这些序列可能耗时且成本高昂。动态心肌MRI是一种快速、无对比剂的成像技术，可以可视化急性MI引起的运动和结构异常。因此，我们提出了一种新的端到端深度神经网络，命名为CineMyoPS，从动态CMR图像中单独分割心肌病理（例如瘢痕和水肿）。具体来说，CineMyoPS提取与MI相关的运动和解剖特征。鉴于这些特征之间的相互依赖性，我们设计了一个一致性损失函数（类似于协同训练策略），以促进它们的联合学习。此外，我们提出了一种时间序列聚合策略，用于在整个心动周期中整合与MI相关的心肌特征，从而提高心肌病理分割的准确性。在多中心数据集上的实验结果表明，CineMyoPS在心肌病理分割、运动估计和解剖结构分割方面取得了令人满意的表现。
URL
https://arxiv.org/abs/2507.02289
PDF
